bhattmanish98 commented on code in PR #8611: URL: https://github.com/apache/hadoop/pull/8611#discussion_r3850186854
########## hadoop-tools/hadoop-azure/src/test/java/org/apache/hadoop/fs/azurebfs/contract/TestArrowListBlobParser.java: ########## @@ -0,0 +1,1193 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.hadoop.fs.azurebfs.contract; + +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; +import java.io.IOException; +import java.io.InputStream; +import java.nio.channels.Channels; +import java.nio.charset.StandardCharsets; +import java.time.LocalDateTime; +import java.time.ZoneOffset; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; + +import org.apache.arrow.memory.ArrowBuf; +import org.apache.arrow.memory.BufferAllocator; +import org.apache.arrow.memory.RootAllocator; +import org.apache.arrow.vector.BigIntVector; +import org.apache.arrow.vector.BitVector; +import org.apache.arrow.vector.TimeStampMilliTZVector; +import org.apache.arrow.vector.TimeStampSecVector; +import org.apache.arrow.vector.UInt8Vector; +import org.apache.arrow.vector.VarCharVector; +import org.apache.arrow.vector.VectorSchemaRoot; +import org.apache.arrow.vector.complex.MapVector; +import org.apache.arrow.vector.complex.impl.UnionMapWriter; +import org.apache.arrow.vector.ipc.ArrowStreamWriter; +import org.apache.arrow.vector.types.TimeUnit; +import org.apache.arrow.vector.types.pojo.ArrowType; +import org.apache.arrow.vector.types.pojo.Field; +import org.apache.arrow.vector.types.pojo.FieldType; +import org.apache.arrow.vector.types.pojo.Schema; +import org.apache.arrow.vector.util.Text; +import org.junit.jupiter.api.Test; + +import org.apache.hadoop.fs.azurebfs.contracts.services.ArrowListBlobParser; +import org.apache.hadoop.fs.azurebfs.contracts.services.BlobListResultEntrySchema; +import org.apache.hadoop.fs.azurebfs.contracts.services.BlobListResultSchema; +import org.apache.hadoop.fs.azurebfs.utils.DateTimeUtils; + +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_CONTENT_LENGTH; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_COMPLETION_TIME; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_ID; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_PROGRESS; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_SOURCE; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_STATUS; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_COPY_STATUS_DESCRIPTION; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_CREATION_TIME; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_ETAG; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_IS_DIRECTORY; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_LAST_MODIFIED; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_METADATA; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_NAME; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_COL_RESOURCE_TYPE; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_METADATA_NEXT_MARKER; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.ARROW_RESOURCE_TYPE_BLOB_PREFIX; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.DIRECTORY; +import static org.apache.hadoop.fs.azurebfs.constants.AbfsHttpConstants.XML_TAG_HDI_ISFOLDER; +import static org.apache.hadoop.fs.azurebfs.constants.HttpHeaderConfigurations.X_MS_META_HDI_ISFOLDER; +import static org.assertj.core.api.Assertions.assertThat; +import static org.assertj.core.api.Assertions.assertThatThrownBy; + +/** + * Unit tests for {@link ArrowListBlobParser}, the Photon (Apache Arrow based) + * ListBlobs response parser. + */ +public class TestArrowListBlobParser { + + private static final String URL = "https://account.blob.core.windows.net/container";; + + /** Generous allocator limit used by the functional parsing tests. */ + private static final long MEMORY_LIMIT = 256L * 1024 * 1024; + + /** Deliberately tiny allocator limit used to force an over-limit failure. */ + private static final long TINY_MEMORY_LIMIT = 1024L; + + /** Arrow integer bit width used for the content-length column. */ + private static final int ARROW_INT_BIT_WIDTH = 64; + + /** Row count large enough to exhaust the tiny allocator limit. */ + private static final int OVER_LIMIT_ROW_COUNT = 2000; + + // Sample content-length values shared between builder rows and assertions. + private static final long CONTENT_LENGTH_A = 20L; + private static final long CONTENT_LENGTH_B = 30L; + private static final long CONTENT_LENGTH_C = 40L; + private static final long CONTENT_LENGTH_D = 42L; + private static final long CONTENT_LENGTH_SAMPLE = 1234L; + + /** + * Verify an Arrow response with a single blob is parsed correctly and all + * common blob properties are populated. + */ + @Test + public void testSingleBlob() throws Exception { + byte[] stream = new ArrowStreamBuilder() + .addRow("file1.txt", "0x8DB6668EAB50E67", CONTENT_LENGTH_SAMPLE, + "Tue, 06 Jun 2023 08:35:00 GMT", + "Tue, 06 Jun 2023 08:34:28 GMT", false) + .build(); + + BlobListResultSchema result = parse(stream); + + assertThat(result.paths()).hasSize(1); + BlobListResultEntrySchema entry = result.paths().get(0); + assertThat(entry.name()).isEqualTo("file1.txt"); + assertThat(entry.path().toUri().getPath()).isEqualTo("/file1.txt"); + assertThat(entry.url()).isEqualTo(URL + "/file1.txt"); + assertThat(entry.eTag()).isEqualTo("0x8DB6668EAB50E67"); + assertThat(entry.contentLength()).isEqualTo(CONTENT_LENGTH_SAMPLE); + assertThat(entry.lastModified()).isEqualTo("Tue, 06 Jun 2023 08:35:00 GMT"); + assertThat(entry.creation()).isEqualTo("Tue, 06 Jun 2023 08:34:28 GMT"); + assertThat(entry.isDirectory()).isFalse(); + } + + /** + * Verify that an ISO-8601 date-time from the Arrow response (as Photon + * serializes timestamps, without an explicit zone) is normalized to the same + * RFC 1123 GMT representation used by the XML ListBlobs path, and that it + * yields the expected epoch when parsed downstream. + */ + @Test + public void testArrowIsoDateTimeNormalizedToRfc1123() throws Exception { + byte[] stream = new ArrowStreamBuilder() + .addRow("file1.txt", "etag", 1L, + "2026-07-06T10:31:19", "2026-07-06T10:30:00", false) + .build(); + + BlobListResultSchema result = parse(stream); + + BlobListResultEntrySchema entry = result.paths().get(0); + assertThat(entry.lastModified()) + .isEqualTo("Mon, 06 Jul 2026 10:31:19 GMT"); + assertThat(entry.creation()) + .isEqualTo("Mon, 06 Jul 2026 10:30:00 GMT"); + + long arrowEpoch = DateTimeUtils.parseLastModifiedTime( + entry.lastModified()); + long xmlEpoch = DateTimeUtils.parseLastModifiedTime( Review Comment: Added testArrowDateWeekdayLeapDayAndJanFeb: 2028-02-29 → Tue and a Jan/Feb date exercising the month < 3 ? year - 1, asserting the weekday. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
